End-to-end Person Search Sequentially Trained on Aggregated Dataset
In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) purpose. We propose a new end-to-end model that jointly computes detection and feature extraction steps through a single deep Convolutional Neural Network architecture. Sharing feature maps between the two tasks for jointly describing people commonalities and specificities allows faster runtime, which is valuable in real-world applications. In addition to reaching state-of-the-art accuracy, this multi-task model can be sequentially trained task-by-task, which results in a broader acceptance of input dataset types. Indeed, we show that aggregating more pedestrian detection datasets without costly identity annotations makes the shared feature maps more generic, and improves re-ID precision. Moreover, these boosted shared feature maps result in re-ID features more robust to a cross-dataset scenario.
Code (0)
등록된 구현이 없습니다.
Tasks
Pedestrian DetectionPerson SearchSimilar Papers 제목 키워드 기반
Sequentially Aggregated Convolutional Networks
Modern deep networks generally implement a certain form of shortcut connections to alleviate optimization difficulties. However, we observe that such network topology alters the nature of deep networks. In many ways, the…
General Classificationimage-classificationImage ClassificationFedAH: Aggregated Head for Personalized Federated Learning
Recently, Federated Learning (FL) has gained popularity for its privacy-preserving and collaborative learning capabilities. Personalized Federated Learning (PFL), building upon FL, aims to address the issue of statistica…
Federated LearningPersonalized Federated LearningPrivacy PreservingChurn-Aware Recommendation Planning under Aggregated Preference Feedback
We study a sequential decision-making problem motivated by recent regulatory and technological shifts that limit access to individual user data in recommender systems (RSs), leaving only population-level preference infor…
DesignPref: Capturing Personal Preferences in Visual Design Generation
Generative models, such as large language models and text-to-image diffusion models, are increasingly used to create visual designs like user interfaces (UIs) and presentation slides. Finetuning and benchmarking these ge…
Active Learning for Regression with Aggregated Outputs
Due to the privacy protection or the difficulty of data collection, we cannot observe individual outputs for each instance, but we can observe aggregated outputs that are summed over multiple instances in a set in some r…
Active LearningGaussian Processesregression